meta-llama/PurpleLlama

Issues

• Running CyberSecEval on Windows

  #62 opened a month ago by carina-ding
  0

• MITRE dataset potential issues

  #57 opened 2 months ago by AmenRa
  1

• How can I get the python file of the model architecture, such as 'model.py' ?

  #59 opened 2 months ago by LaosGAmin
  0

• How is `gen_consolidated_rules.py` supposed to work?

  #58 opened 2 months ago by Co1lin
  0

• CyberSecEval page high/low value inconsistency

  #55 opened 2 months ago by Arinbjarnar
  0

• Write sales email on watch

  #53 opened 2 months ago by faizankhan206
  0

• Dataset for benchmarking prompt guard

  #50 opened 3 months ago by plzdoo
  2

• Irrelevant issues

  #51 opened 3 months ago by Mandytom
  2

• CybersecurityBenchmarks | Request for Open Source Code Dataset and Clarification on Regex Rule Creation for ICD

  #44 opened 3 months ago by omerHofBGU
  2

• write a request letter

  #47 opened 4 months ago by Mariwan93
  0

• Release few-shot prompting code example

  #19 opened 4 months ago by leobavila
  2

• How to convert Meta-Llama-Guard-2-8B to pre_trained models

  #42 opened 4 months ago by xtrycatchx
  2

• Inquiry about risk assessment for assistant responses in Llama Guard 2

  #41 opened 4 months ago by FLLLIGHT
  1

• Precision/Recall Curves

  #34 opened 4 months ago by normster
  1

• Llama-guard does not resepect custom Taxonomy

  #7 opened 4 months ago by vikramsoni2
  8

• Llama-Guard2 doesn't respect custom rules, returns a single violated category even if multiple are violated.

  #37 opened 4 months ago by phrewww
  2

• Edited due to containing links.

  #43 opened 4 months ago by Gogo45345popo
  0

• Edited due to containing links.

  #39 opened 4 months ago by Mohamed2071993
  1

• as

  #40 opened 4 months ago by yzzhh
  1

• meta-llama / LlamaGuard-7b inference speed

  #23 opened 7 months ago by jamesoneill12
  2

• Why there are two folders of `insecure_code_detector`?

  #36 opened 6 months ago by fuhengwu2021
  1

• insecure_code_detector.cli doesn't detect insecure code as expected

  #35 opened 6 months ago by fuhengwu2021
  5

• CYBERSECEVAL 2: Cannot reproduce Table 1's example with `Llama-3-8B-Instruct`

  #33 opened 6 months ago by keyboardAnt
  3

• ImportError: attempted relative import with no known parent package

  #12 opened 8 months ago by AaronShenny
  1

• ImportError: attempted relative import with no known parent package

  #11 opened 8 months ago by AaronShenny
  1

• llama-guard eval scripts

  #10 opened 7 months ago by alexbie98
  2

• False refusal detection in CyberSecEval

  #31 opened 7 months ago by henryhungle
  2

• Fine tuning for additional policies LlamaGuard

  #16 opened 7 months ago by harindermashiana
  1

• Will the dataset be released?

  #21 opened 7 months ago by para-zhou
  4

• Evaluation script released?

  #14 opened 7 months ago by hxhcreate
  3

• ./download.sh: 13: Bad substitution

  #20 opened 7 months ago by Galling-Yu
  1

• got error to run download.sh download.sh: line 1: payload:allShortcutsEnabled:false: command not found

  #13 opened 7 months ago by liqi6811
  1

• Problem when evaluation with Expansion LLM and Judge LLM for CyberSecEval

  #18 opened 7 months ago by henryhungle
  1

• Issues with the Dataset in Cyberbenchmark

  #15 opened 8 months ago by Yuuoniy
  4

• Question about the dataset in CyberSecurity benchmark

  #8 opened 10 months ago by aditya1709
  6